CMMT: Cross-Modal Meta-Transformer for Video-Text Retrieval.
Yizhao GaoZhiwu LuPublished in: ICMR (2023)
Keyphrases
- text retrieval
- cross modal
- multimedia retrieval
- image retrieval
- multi modal
- visual data
- multimedia
- multimedia data
- document collections
- video sequences
- information retrieval
- video content
- query expansion
- video data
- multimedia information retrieval
- semantic concepts
- document retrieval
- retrieval systems
- retrieval model
- image database
- video analysis
- video frames
- content based retrieval
- multimedia databases
- video retrieval
- visual features
- metadata
- visual content
- key frames
- visual information
- test collection
- visual recognition
- space time